Multimodal agent produces illustrated research reports with controllable detail
MIRA: A Multimodal Illustrated Deep Research Agent for Controllable Reports
Computer Vision and Pattern Recognition
Summary
Creating detailed research reports that include both text and images from the web is hard because existing tools don't use pictures well and are rigid in how they report findings. The authors developed MIRA, a smart agent that collects and integrates both text and images during research and writing. MIRA can follow user instructions about how detailed and visual the report should be and can revise its reports based on feedback. The system shows improved performance compared to other open tools and delivers reports with clear links to their sources.
What this means in practice
- •For technical writers: Produce customizable illustrated reports integrating text and images sourced through complex web searches aligned with specific user instructions.
- •For content development teams: Generate evidence-backed, multimodal research documents that can be revised iteratively based on feedback before final delivery.
Authors
Hongrui Wu, Kaiwen Tuo, Congcong Wang, Gen Li, Shuai Dong, Xinlei Yu, Yuqi Xu, Haowen Hou, Zelin Peng, Jiaqi Wang
Abstract
Deep research agents are increasingly capable of searching the open web and synthesizing evidence, yet they remain poorly suited to controllable report generation in multimodal deep research. This task requires agents to handle interleaved textual and visual inputs, gather multimodal evidence through multi-step web search, and deliver comprehensive illustrated reports under user-specified requirements. Existing systems face two limitations. During reasoning, they often underuse images discovered along the search trajectory; during generation, they tend to produce fixed-form answers with limited control over report granularity, multimodal composition, and evidence grounding. We introduce MIRA, a Multimodal Illustrated Deep Research Agent for controllable reports. MIRA integrates textual and visual evidence throughout research and writing. At its core, MIRA-Harness translates user requirements into generation contracts and connects four stages: evidence collection, report submission, feedback-driven revision, and final delivery. Building on this harness, MIRA-Data constructs high-quality multi-hop multimodal research trajectories, and we post-train foundation models to operate within the workflow. Using Qwen3.6-35B-A3B, MIRA achieves state-of-the-art performance among open agents on 7 representative, established multimodal-search and deep-research-agent benchmarks, while producing user-aligned illustrated reports with traceable textual and visual evidence.